Machine Learning Methods for Data-Driven Identification of Target Processes in the Context of Process Mining (DISP)

Background:

The use of machine learning in the context of process mining has recently met with growing interest. The reason for this is that so far, for example in process discovery, only methods of exploratory data analysis have been used. Recent approaches aim at improving this user-driven approach of process mining by using and combining it with machine learning (ML) techniques. This is expected to provide valuable and fully automated insights into business processes. It intelligently analyzes business processes to uncover hidden problems and provide real-time recommendations for process improvement, as well as understand workflows, derive conclusions, explore root causes of process violations, and recommend actions. This transforms traditional process mining - as an exploratory BI method - into an intelligent method of process analysis.

Main research question:

How can machine learning enable process mining for knowledge identification?

The main research question investigates:

Investigate the use of machine learning in the context of process mining, for automated insights into business processes.

Research objective:

The goal of the overall project is to build and extend approaches to intelligent process mining.